© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 3635
    Prev
    Next
    INDEX
    Explanations

    foreign words

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron strongly activates on unusually long runs of leading whitespace (deep indentation) at the start of lines.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     автофо
    0.84
     ListItem
    0.84
     الط
    0.82
     ካ
    0.82
    ीय
    0.81
     وب
    0.80
     Arte
    0.80
    icida
    0.79
    窕
    0.79
     reaff
    0.78
    POSITIVE LOGITS
    ’
    0.85
    Однако
    0.82
     godine
    0.79
    をしている
    0.77
    January
    0.76
    ways
    0.76
    โครงการ
    0.76
    יש
    0.76
    Iam
    0.75
    .
    0.75
    Activations Density 0.000%

    No Known Activations